Skip to main content

What are you building?

Pick a workload. We'll match you with the cheapest GPU and show the true monthly cost — including storage and network.

Generate Images

Stable Diffusion, ControlNet, or ComfyUI

12 GB VRAM~150 GB storage
ComfyUISDXLControlNet

Cheapest options

at 20 hrs/week
V100Vast.ai
$2/mo
V100Vast.ai
$3/mo
RTX5060TiVast.ai
$4/mo

Total includes compute, storage, and egress. Spot pricing excluded.

Fine-tune a Model

LoRA or QLoRA fine-tuning on your own data

24 GB VRAM~250 GB storage
HuggingFace PEFTbitsandbytesAxolotl

Cheapest options

at 30 hrs/week
V100 x2Vast.ai
$10/mo
A100Vast.ai
$12/mo
V100 x4Vast.ai
$16/mo

Total includes compute, storage, and egress. Spot pricing excluded.

Serve an LLM API

Run Llama 70B or similar with vLLM or TGI

80 GB VRAM2+ GPUs~200 GB storage
vLLMTGIFastAPI

Cheapest options

at 24/7
A4500 x4RunPod
$572/mo
A4000 x5RunPod
$637/mo
A40 x2RunPod
$659/mo

Total includes compute, storage, and egress. Spot pricing excluded.

Train from Scratch

Multi-GPU pre-training with DeepSpeed or FSDP

80 GB VRAM4+ GPUs~1 TB storage
DeepSpeedFSDPWeights & Biases

Cheapest options

at 24/7
A4500 x4RunPod
$633/mo
A4000 x5RunPod
$698/mo
RTX3090 x4RunPod
$720/mo

Total includes compute, storage, and egress. Spot pricing excluded.

Generate Video

CogVideoX, Mochi, or LTX-Video

24 GB VRAM~300 GB storage
CogVideoXdiffusersFFMPEG

Cheapest options

at 40 hrs/week
V100 x2Vast.ai
$14/mo
A100Vast.ai
$16/mo
V100 x4Vast.ai
$21/mo

Total includes compute, storage, and egress. Spot pricing excluded.